Skip to content
Model Pareto

Compare models

Side by side: quality per category, price, speed, and every benchmark cell with where it came from. Pick up to four.
SkyReels V4Gemini Omni FlashGemini Omni 1.1 FlashWan 3.0Up to 4 models — remove one to add another.
Focus

Video generation: quality vs price

Compared models are ringed; the other 30 ranked here are greyed.

Lower price is better. Pareto frontier: Hailuo 2.3, Grok Imagine Video, HiDream-O1-Video, Gemini Omni Flash. 4 models are not plotted: Muse Video, MAGI-2 Preview, Bach-1.0 Preview, Cosmos3-Super-Image2Video-4Step.

4 models with no price data — shown in the strip at the left edge

Muse Video, MAGI-2 Preview, Bach-1.0 Preview, Cosmos3-Super-Image2Video-4Step

  • Best-value frontier (nothing is both cheaper and better)
  • Evidencestrong → weak
  • Estimated from other categories
  • SkyReels V4
    Quality
    48.9
    Rank
    #17/34
    Price
    $0.35/s
    Speed
    —

    vs Gemini Omni Flash: −48.0 quality · 3.5× price

  • Gemini Omni Flash
    Quality
    96.9
    Rank
    #1/34
    Price
    $0.10/s
    Speed
    —

    vs Gemini Omni 1.1 Flash: +2.6 quality · 1× price

  • Gemini Omni 1.1 Flash
    Quality
    94.3
    Rank
    #2/34
    Price
    $0.10/s
    Speed
    —

    vs Gemini Omni Flash: −2.6 quality · 1× price

  • Wan 3.0
    Quality
    93.8
    Rank
    #3/34
    Price
    $0.20/s
    Speed
    —

    vs Gemini Omni Flash: −3.1 quality · 2× price

Overview

Lab
Skywork AI
Google DeepMind
Google DeepMind
Alibaba Qwen
Released
Feb 25, 2026
May 19, 2026
Aug 27, 2026
Aug 19, 2026
Weights
Proprietary
Proprietary
Proprietary
Proprietary
Price per second
1080p
$0.35
$0.10Best
$0.10Best
$0.20

Quality by category

0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.

48.9±5.7
#17/34Verified
96.9±3.0Best
#1/34Verifiedbest value
94.3±6.3
#2/34Verified
93.8±4.1
#3/34Verified

Video generation benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

VBench
day 0
—
—
—
—